Skills
skills/gooseworks-ai/goose-skills/browser-automation-notte/Gen Agent Trust Hub

browser-automation-notte

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXPOSURE]: The skill reads authentication credentials from ~/.gooseworks/credentials.json to access the author's browser automation platform. This is a standard procedure for this vendor's services.
  • [COMMAND_EXECUTION]: Uses python3 -c to extract keys from local configuration files and npx to execute the vendor's login utility for setup.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external websites, which presents a surface for indirect prompt injection.
  • Ingestion points: Web content retrieved via Scrape Webpage, Scrape Page, and autonomous tasks in Start Agent.
  • Boundary markers: Not explicitly defined in the instruction set.
  • Capability inventory: Includes browser interaction through Execute Page Action and autonomous task execution via Start Agent.
  • Sanitization: No specific sanitization or filtering of external content is documented within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:05 PM